Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1394 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.5402. Min Act: -0.0000

Data Index: 1373160 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.3434. Min Act: -0.0000

Data Index: 1546613 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.3623. Min Act: -0.0000

Data Index: 1515494 (Python Code)

Max Activating Token Index: 626

Text #3

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.4097. Min Act: -0.0000

Data Index: 561220 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.5382. Min Act: -0.0000

Data Index: 166757 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.2889. Min Act: -0.0000

Data Index: 1594283 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.3039. Min Act: -0.0000

Data Index: 1364558 (Python Code)

Max Activating Token Index: 275

Text #7

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.3712. Min Act: -0.0000

Data Index: 211586 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.2690. Min Act: -0.0000

Data Index: 235993 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.2355. Min Act: -0.0000

Data Index: 278285 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.2424. Min Act: -0.0000

Data Index: 311159 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1648685 (Python Code)

Max Activating Token Index: 509

Text #12

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1637741 (Python Code)

Max Activating Token Index: 805

Text #13

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.1964. Min Act: -0.0000

Data Index: 406715 (C4 (Web Text))

Max Activating Token Index: 169

Text #14

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.0468. Min Act: -0.0000

Data Index: 1419299 (Python Code)

Max Activating Token Index: 96

Text #15

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1007379 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.1742. Min Act: -0.0000

Data Index: 1434251 (Python Code)

Max Activating Token Index: 348

Text #17

Max Range: 1.5402. Min Range: -1.5402

Max Act: 0.7742. Min Act: -0.0000

Data Index: 1468067 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.1186. Min Act: -0.0000

Data Index: 294780 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.5402. Min Range: -1.5402

Max Act: 1.2278. Min Act: -0.0000

Data Index: 46924 (C4 (Web Text))

Max Activating Token Index: 855